Premium
Some Extensions of Buser and Baroni‐Urbani's Clustering Method
Author(s) -
Dragomirescu L.
Publication year - 1987
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710290317
Subject(s) - jaccard index , homogeneity (statistics) , cluster analysis , binary number , computer science , algorithm , mathematics , artificial intelligence , statistics , arithmetic
We consider that the algorithm of numerical taxonomy focused upon the concept of “homogeneity”, proposed by Buser and Baroni‐Urbani (1982) for binary data, satisfies best from all the other algorithms known by us, the conditions of classification in biology formulated by Beckner in 1959. Therefore the paper proposes and studies homogeneities for binary and for ordered multi‐states data, which model explicitly Beckner's conditions. From all these, the homogeneity denoted by h * has the remarkable quality of generalizing the famous Jaccard's similarity coefficient. Moreover, using h * in this algorithm “naturally” improved by us, we can achieve the performance of a correct classification of the remarkable example proposed by Watanabe (1969).